AIセキュリティポータルbot

The Use of Large Language Models (LLM) for Cyber Threat Intelligence (CTI) in Cybercrime Forums

Authors: Vanessa Clairoux-Trepanier, Isa-May Beauchamp, Estelle Ruellan, Masarah Paquet-Clouston, Serge-Olivier Paquette, Eric Clay | Published: 2024-08-06 | Updated: 2024-10-01
LLM Performance Evaluation
Data Collection
Variable Extraction Method
2024.08.06 2025.05.27
Literature Database

Compromising Embodied Agents with Contextual Backdoor Attacks

Authors: Aishan Liu, Yuguang Zhou, Xianglong Liu, Tianyuan Zhang, Siyuan Liang, Jiakai Wang, Yanjun Pu, Tianlin Li, Junqi Zhang, Wenbo Zhou, Qing Guo, Dacheng Tao | Published: 2024-08-06
Backdoor Attack
Prompt Injection
2024.08.06 2025.05.27
Literature Database

Hide and Seek: Fingerprinting Large Language Models with Evolutionary Learning

Authors: Dmitri Iourovitski, Sanat Sharma, Rakshak Talwar | Published: 2024-08-06
LLM Performance Evaluation
Prompt Injection
Model Performance Evaluation
2024.08.06 2025.05.27
Literature Database

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services

Authors: Shaopeng Fu, Xuexue Sun, Ke Qing, Tianhang Zheng, Di Wang | Published: 2024-08-05
Privacy Protection Method
Membership Inference
Attack Method
2024.08.05 2025.05.27
Literature Database

Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense

Authors: Qilei Li, Ahmed M. Abdelmoniem | Published: 2024-08-05 | Updated: 2024-08-16
DoS Mitigation
Poisoning
Defense Method
2024.08.05 2025.05.27
Literature Database

Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?

Authors: Mohammad Bahrami Karkevandi, Nishant Vishwamitra, Peyman Najafirad | Published: 2024-08-05
Prompt Injection
Reinforcement Learning
Adversarial Example
2024.08.05 2025.05.27
Literature Database

Practical Attacks against Black-box Code Completion Engines

Authors: Slobodan Jenko, Jingxuan He, Niels Mündler, Mark Vero, Martin Vechev | Published: 2024-08-05
Attack Method
Vulnerability Management
Evaluation Method
2024.08.05 2025.05.27
Literature Database

Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models

Authors: Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Haoyang Li | Published: 2024-08-05 | Updated: 2025-02-12
Prompt Injection
Prompt leaking
Model Evaluation
2024.08.05 2025.05.27
Literature Database

From Generalist to Specialist: Exploring CWE-Specific Vulnerability Detection

Authors: Syafiq Al Atiiq, Christian Gehrmann, Kevin Dahlén, Karim Khalil | Published: 2024-08-05
LLM Performance Evaluation
Model Performance Evaluation
Vulnerability Management
2024.08.05 2025.05.27
Literature Database

Quantum Clustering for Cybersecurity

Authors: Walid El Maouaki, Nouhaila Innan, Alberto Marchisio, Taoufik Said, Mohamed Bennai, Muhammad Shafique | Published: 2024-08-05
Algorithm
Cybersecurity
Quantum Framework
2024.08.05 2025.05.27
Literature Database
Next page